AI agents call hg_status to retrieve information from Mercurial without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
hg_status is a read-only operation that retrieves and displays the current state of files in the working directory (modified, added, removed, untracked, etc.). It performs no modifications, deletions, or execution of code. The blast radius if misused by an AI agent is minimal—the worst outcome would be the agent seeing repository state information, which is informational only.
From the tool's definition Tool name 'hg_status' and description 'Shows the working directory status' indicate a query operation with no side effects. This aligns with standard version control status commands that only retrieve information about file states.
Attacks that exploit this kind of access
Shows the working directory status. It is categorised as a Read tool in the Mercurial MCP Server, which means it retrieves data without modifying state.
Register the Mercurial MCP server in PolicyLayer and add a rule for hg_status: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mercurial. Nothing to install.
hg_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the hg_status rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for hg_status. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
hg_status is provided by the Mercurial MCP server (metal-shark-sharktech/mcp-server-mercurial). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →